mint-recon
Pass
Audited by Gen Agent Trust Hub on Jun 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes bash commands (
find,grep,xargs) in Step 0 to search the project directory for files containing financial keywords. These commands are used to identify relevant data artifacts for analysis. - [PROMPT_INJECTION]: The skill processes untrusted data from local files (Markdown, CSV, JSON) which are identified during the scanning process. This presents an indirect prompt injection surface where malicious content within those files could attempt to influence the agent's summary or next actions.
- Ingestion points: Files matching financial keywords are identified and read in SKILL.md Step 0.
- Boundary markers: No specific delimiters or instructions are provided to the agent to treat file content as data only.
- Capability inventory: The skill uses
ReadandBashtools to access and process the files. - Sanitization: There is no evidence of sanitization or validation of the file content before it is processed by the agent.
Audit Metadata